ChipSeg: An Automatic Tool to Segment Bacterial and Mammalian Cells Cultured in Microfluidic Devices

Cesare, Irene de; Zamora-Chimal, Criseida G.; Postiglione, Lorena; Khazim, Mahmoud; Pedone, Elisa; Shannon, Barbara; Fiore, Gianfranco Beniamino; Perrino, Giansimone; Napolitano, Sara; Bernardo, Diego di; Savery, Nigel J.; Bernardo, Mario di; Marucci, Lucia

doi:10.1021/acsomega.0c03906

Cited by 14 publications

(24 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We show that Cheetah can rapidly compute highly accurate image segmentation (99.2% and 98.8% for E. coli and mESCs, respectively) even when trained using only a small number of manually annotated images (2 and 34 images for E. coli and mESCs, respectively). This exceeded the performance of ChipSeg 12,35 which achieved 96.1% and 74% accuracy for the same E. coli and mESCs data, respectively, and is comparable to other deep learning approaches (e.g. Delta which reaches 99.86% accuracy for bacteria when trained on a much larger set of images 37 ).…”

Section: Discussionmentioning

confidence: 47%

“…walls and imperfections in the fabrication) causing high contrast features that were incorrectly classified as cells. It should be noted that improved segmentation performance using the Otsu method can be achieved through pre-processing of images to crop out unwanted features like the chamber walls 33 . Such pre-processing was not performed here because for control applications it is often necessary to image over long-time courses, which can cause a drift in the images produced as many chambers are imaged sequentially.…”

Section: Discussionmentioning

confidence: 99%

“…Masked images were obtained using the global thresholding strategy. For further details and access to the code, we refer the reader to de Cesare et al 33…”

Section: Otsu Thresholding-based Segmentation Algorithmmentioning

confidence: 99%

“…Then, MATLAB functions implementing the Otsu method are executed, followed by the addiction of morphological operator to reshape the segmentation result. For further details and access to the code see de Cesare et al 35 The final mask contained the boundaries and interiors of every segmented cell. This mask was overlaid to the fluorescence image field to calculate the fluorescence as the sum of all pixels in the segmented area minus the background fluorescence value.…”

Section: Chipseg Segmentationmentioning

confidence: 99%

“…We demonstrate its core functionality and flexibility by both post-processing time-lapse data for bacterial and mammalian cell growth in a microfluidic chip and external feedback control of gene expression in mammalian cells. We demonstrate Cheetah's increased robustness compared to the widely used Otsu thresholding-based method 12,33 and show how poor segmentation can lead to miscomputed control error and the possible failure of an experiment. Cheetah has a broad range of potential applications from post-experiment image analysis to robust real-time feedback control.…”

Section: Introductionmentioning

confidence: 97%

See 4 more Smart Citations

Cheetah: a computational toolkit for cybergenetic control

Pedone

Cesare

Zamora

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

1Advances in microscopy, microfluidics and optogenetics enable single cell monitoring and 2 environmental regulation and offer the means to control cellular phenotypes. The development 3 of such systems is challenging and often results in bespoke setups that hinder reproducibility. To 4 address this, we introduce Cheetah -a flexible computational toolkit that simplifies the integration 5 of real-time microscopy analysis with algorithms for cellular control. Central to the platform is an 6 image segmentation system based on the versatile U-Net convolutional neural network. This is 7 supplemented with functionality to robustly count, characterise and control cells over time. We 8 demonstrate Cheetah's core capabilities by analysing long-term bacterial and mammalian cell 9 growth and by dynamically controlling protein expression in mammalian cells. In all cases, 10 Cheetah's segmentation accuracy exceeds that of a commonly used thresholding-based method, 11 allowing for more accurate control signals to be generated. Availability of this easy-to-use 12 platform will make control engineering techniques more accessible and offer new ways to probe 13 and manipulate living cells. 14 Introduction 15Modern automated microscopy techniques enable researchers to collect vast amounts of single-16 cell imaging data at high temporal resolutions. This has resulted in time-lapse microscopy 17 becoming the go to method for studying cellular dynamics, enabling the quantification of 18 processes such as stochastic fluctuations during gene expression 1-3 , emerging oscillatory 19 patterns in protein concentrations 4 , lineage selection 5,6 , and many more 7 . 20To make sense of microscopy images, segmentation is performed whereby an image is 21 broken up into regions corresponding to specific features of interest (e.g. cells and the 22 background). Image segmentation allows for the accurate quantification of cellular phenotypes 23 encoded by visual cues (e.g. fluorescence) by ensuring only those pixels corresponding to a cell 24 are considered. A range of segmentation algorithms have been proposed to automatically 25 analyse images of various organisms and tissues 3,8-11 . The most common of these are 26 thresholding 12 and seeded watershed 13 methods, which are available in many scientific image 27 processing toolkits. Commercial software packages also implement this type of functionality, 28 enabling both automated image acquisition and analysis (e.g. NIS-Elements, Nikon). While these 29 proprietary systems are user-friendly requiring no programming skills to be used, they are often 30 difficult to tailor for specific needs and cannot be easily extended to new forms of analysis. 31More recently, deep learning-based approaches to image segmentation have emerged 32 7,14-17 . Compared to the more common thresholding-based approaches 12 , deep learning methods 33 tend to require more significant computational resources when running on traditional computer 34 architectures and often require the time-consuming manual step of generating...

show abstract

Section: Discussionmentioning

confidence: 47%

Section: Discussionmentioning

confidence: 99%

“…Masked images were obtained using the global thresholding strategy. For further details and access to the code, we refer the reader to de Cesare et al 33…”

Section: Otsu Thresholding-based Segmentation Algorithmmentioning

confidence: 99%

Section: Chipseg Segmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 97%

See 3 more Smart Citations

Cheetah: a computational toolkit for cybergenetic control

Pedone

Cesare

Zamora

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Mechanistic Model-Driven Biodesign in Mammalian Synthetic Biology

Chew,

Marucci

2024

Methods in Molecular Biology

View full text Add to dashboard Cite

Investigation of Different Free Image Analysis Software for High-Throughput Droplet Detection

et al. 2021

View full text Add to dashboard Cite

Droplet microfluidics has revealed innovative strategies in biology and chemistry. This advancement has delivered novel quantification methods, such as droplet digital polymerase chain reaction (ddPCR) and an antibiotic heteroresistance analysis tool. For droplet analysis, researchers often use image-based detection techniques. Unfortunately, the analysis of images may require specific tools or programming skills to produce the expected results. In order to address the issue, we explore the potential use of standalone freely available software to perform image-based droplet detection. We select the four most popular software and classify them into rule-based and machine learning-based types after assessing the software’s modules. We test and evaluate the software’s (i) ability to detect droplets, (ii) accuracy and precision, and (iii) overall components and supporting material. In our experimental setting, we find that the rule-based type of software is better suited for image-based droplet detection. The rule-based type of software also has a simpler workflow or pipeline, especially aimed for non-experienced users. In our case, CellProfiler (CP) offers the most user-friendly experience for both single image and batch processing analyses.

show abstract

ChipSeg: An Automatic Tool to Segment Bacterial and Mammalian Cells Cultured in Microfluidic Devices

Cited by 14 publications

References 29 publications

Cheetah: a computational toolkit for cybergenetic control

Cheetah: a computational toolkit for cybergenetic control

Mechanistic Model-Driven Biodesign in Mammalian Synthetic Biology

Investigation of Different Free Image Analysis Software for High-Throughput Droplet Detection

Contact Info

Product

Resources

About